openspec-apply-change
Skill20 starsChanged 20 days agoApache-2.0View on GitHub
Implements the pending tasks of an OpenSpec change against its proposal, specs, and design, looping until done or blocked. Use for "implement this change", "start/continue implementing", "work through the tasks", or "keep going on <change>". Can be invoked any time tasks exist, before or after other artifacts are finished, and interleaved with artifact updates — it is not phase-locked to a single point in the change's lifecycle.
147 other projects use a version of this.
Adopted by
Most recently taken up by
- ValorVie/custom-skillstheir own version, first seen Nov 8, 2026
- full-stack-skills/electron-skillstheir own version, first seen Nov 8, 2026
- halo-dev/plugin-ai-foundationtheir own version, first seen Nov 8, 2026
- ptonlix/OneSelftheir own version, first seen Nov 8, 2026
- FuDesign2008/open-skillstheir own version, first seen Nov 6, 2026
- feimacode/open-design-agent-kittheir own version, first seen Nov 6, 2026
Used with
Projects with it also use source-command-opsx-apply, source-command-opsx-archive and 4 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
antech2-asyncSkillsource-command-opsx-apply
Implement tasks from an OpenSpec change (Experimental)
Also in 5 projects that use this
antech2-asyncSkillsource-command-opsx-archive
Archive a completed change in the experimental workflow
Also in 5 projects that use this
Microsoft AzureSkillopenspec-update-change
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.
Also in 89 projects that use this
goernSkilldraft-openspec-docs
Collaborative page-drafting mode for the OpenSpec docs. Builds a scratch plan inside the target page (purpose, structure, numbered draft steps), iterates on it with the user, then drafts one section per approved step and cleans up after itself. Use when a page needs a from-scratch rewrite or a new page is being shaped with the user in the loop.
Also in 3 projects that use this
- +2 more from antech2-async
Other versions147 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 147
- Fission-AI/OpenSpec★ 74ksame name
- halo-dev/halo★ 40ksame name
- alibaba/druid★ 28ksame name
- studyzy/imewlconverter★ 10ksame name
- databasus/databasus★ 9.3ksame name
- RostislavDugin/postgresus★ 9.3ksame name
- fonoster/fonoster★ 8.2ksame name
- fleetdm/fleet★ 7.2ksame name
- PBH-BTN/PeerBanHelper★ 6.4ksame name
- KunAgent/Kun★ 6.4ksame name
137 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository73 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- rhdh-base-imagesSkill
- rhdh-konflux-rpaSkill
- rhdh-konflux-tasksSkill
- rhdh-plugin-catalog-index-status-and-update-flowSkill
- rhdh-pr-mrSkill
- rhdh-prow-jobsSkill
- rhdh-prow-release-branchSkill
- rhdh-prow-triggerSkill
- rhdh-yarn-bumpSkill
- rhdh-feature-docsSkill
- rhdh-jira-createSkill
- rhdh-jira-linkSkill
- rhdh-jira-refineSkill
- rhdh-jira-sprint-planSkill
- rhdh-jira-sprint-reportSkill
- rhdh-jira-updateSkill
- rhdh-prepare-refinementSkill
- agent-readinessSkill
- ask-rhdhSkill
- clean-proseSkill
- setup-rhdh-skillsSkill
- skill-authoringSkill
- rhdh-backportSkill
- rhdh-backstage-upgradeSkill
- rhdh-localSkill
- rhdh-operator-pr-testSkill
- rhdh-overlaySkill
- rhdh-playwrightSkill
- rhdh-plugin-authoringSkill
- rhdh-plugin-bug-fixSkill
- rhdh-plugin-exportSkill
- rhdh-plugin-midstream-propagateSkill
- rhdh-plugin-nfs-migrationSkill
- rhdh-plugin-wiringSkill
- rhdh-pr-createSkill
- rhdh-pr-reviewSkill
- rhdh-test-placementSkill
- backstage-api-changesSkill
- mutation-gateSkill
- openspec-journalSkill
- prose-editingSkill
- rhdh-contextSkill
- rhdh-forgeSkill
- rhdh-jira-apiSkill
- rhdh-jira-authoringSkill
- rhdh-spec-driven-schemaSkill
- openspec-archive-changeSkill
- openspec-audit-changeSkill
- openspec-bulk-archive-changeSkill
- openspec-continue-changeSkill
- openspec-exploreSkill
- openspec-ff-changeSkill
- openspec-new-changeSkill
- openspec-onboardSkill
- openspec-sync-specsSkill
- openspec-verify-changeSkill
- rhdh-overlay-cve-exportSkill
- rhdh-platform-lifecycleSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
6 rules. 1 is common, 2 are distinctive, and 3 are very specific to this project.
1
Common
Most of the 143 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
Select the change: Use a given name; otherwise infer from context, or auto-select if only one active change exists.
- Very specific: line 36
Read every file listed under
contextFiles: before starting — for rhdh-spec-driven that is proposal, specs, design, and tasks. - Distinctive: line 65
Always read context files before starting.
- Common: line 66
Keep changes minimal and scoped to each task.
- Very specific: line 68
Use contextFiles from the CLI output.
- Distinctive: line 69
If implementation reveals a design issue, pause and suggest an artifact update rather than silently diverging from the design.
“Common” is measured: kept by at least 6 in 10 of the 143 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Implement OpenSpec change tasks
Work through a change's task checklist against real code, one task at a time, checking each off only once it is actually done.
Steps
- Select the change. Use a given name; otherwise infer from context, or
auto-select if only one active change exists. If ambiguous, run
openspec list --jsonand let the user choose. Always announce which change is in use. - Check status:
openspec status --change "<name>" --json— readschemaNameand which artifact holds the tasks. Get apply instructions:
openspec instructions apply --change "<name>" --jsonReturns
contextFiles(artifact ID -> file paths), task progress, the task list with status, and a dynamic instruction. Ifstate: "blocked"(missing artifacts), suggest/openspec-continue-change. Ifstate: "all_done", congratulate and suggest/openspec-archive-change.- Read every file listed under
contextFilesbefore starting — forrhdh-spec-driventhat is proposal, specs, design, and tasks. - Choose an execution mode for this run, per
/rhdh-spec-driven-schema'sschema.yamlapply block: direct mode for mechanical, low-risk work; team mode (implementer + independent verifier subagents) for semantically complex, ADR-bound, or broad cross-layer work. Announce the choice and rationale before making changes; do not silently switch mid-run. - Work through pending tasks until done or blocked: show which task is
active, make minimal focused changes, flip
- [ ]to- [x]immediately on completion, continue to the next task. Pause on an unclear task, a design issue surfaced by implementation, an error, or user interruption. - Journal as you go, invoking
/openspec-journal:mode.chosenonce at start,task.start/task.completeper task (or per assigned range in team mode),verifier.resultper verdict in team mode,task.blockedon pause,decisionfor load-bearing calls,handoffas the last line before stopping and the first line on resume. Also keep the default turn bookending (turn.start/turn.end) described there. - On completion or pause, show status: tasks completed this session, overall progress (N/M), and either a suggestion to archive or an explanation of the pause with options.
Output
During implementation, show each task starting and completing. On completion, show final progress and readiness to archive. On pause, show the issue, 2-3 options, and "Other approach", then wait.
Guardrails
- Always read context files before starting.
- Keep changes minimal and scoped to each task.
- Pause on errors, blockers, or unclear requirements — never guess.
- Use
contextFilesfrom the CLI output; never assume file names. - If implementation reveals a design issue, pause and suggest an artifact update rather than silently diverging from the design.
Completion
Complete when every task attempted this session is either checked off with matching code changes, or explicitly reported as paused with the reason and options — never left silently half-done — and the apply-phase journal events for the session were written.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

